perhaps this is similar to what you're looking for: the Learner Translator Corpus (http://corpus.leeds.ac.uk/mellange/ltc.html) of the MeLLANGE project (http://mellange.eila.jussieu.fr/). The included translations are also annotated with translation errors, according to a detailed error typology.
Best regards, Mark
On Wed, Jan 11, 2012 at 10:20 PM, Lisa N. Michaud
<michaudl at merrimack.edu> wrote:
> My apologies for the cross-posting; I posted this on CALICO and it was
> suggested that I reach out to this community as well.
> I am working on adapting machine translation metrics for the purpose of
> evaluating student-written translations from source text (both in terms of
> generating an overall "score" for accuracy and identifying the nature/source
> of errors). My current application is for students learning ancient
> languages, translating texts from the L2 into their L1, but I can imagine
> other applications as well.
> What I need for the next step in this project is a large collection of
> translations written by students. I know that translating text is something
> done more with ancient/dead languages than modern languages, and my local
> colleagues can't really help, but I was hoping someone in this community
> might do exercises with his or her students that might fit the bill.
> Let me know if you are interested - and thanks in advance!
> Dr. Lisa N. Michaud, Assistant Professor of Computer Science
> Merrimack College, North Andover, Massachusetts
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no